文献类型：期刊文献

英文题名：A metric learning-based method using graph neural network for pancreatic cystic neoplasm classification from CTs

作者：Zhang, Jiachen[1];Mao, Yishen[2];Li, Ji[2];Li, Yiru[1];Luo, Jianxu[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China;[2]Fudan Univ, Dept Pancreas Surg, Huashan Hosp, Shanghai, Peoples R China

年份：2022

卷号：49

期号：8

起止页码：5523

外文期刊名：MEDICAL PHYSICS

收录：;EI(收录号：20222212182909);WOS:【SCI-EXPANDED(收录号:WOS:000804141600001)】；

基金：Science and Technology Commission of Shanghai Municipality, Grant/Award Number: 19511121203; National Natural Science Foundation of China, Grant/Award Number: 81772566

语种：英文

外文关键词：computer-aided diagnosis; graph neural network; pancreatic cystic neoplasm

摘要：Purpose Pancreatic cystic neoplasms (PCNs) are relatively rare neoplasms and difficult to be classified preoperatively. Ordinary deep learning methods have great potential to provide support for doctors in PCNs classification but require a quantity of labeled samples and exact segmentation of neoplasm. The proposed metric learning-based method using graph neural network (GNN) aims to overcome the limitations brought by small and imbalanced dataset and get fast and accurate PCNs classification result from computed tomography (CT) images. Methods The proposed framework applies GNN. GNNs perform well in fusing information and modeling relational data and get better results on dataset with small size. Based on metric learning strategy, model learns distance from the data. The similarity-based algorithm enhances the classification performance, and more characteristic information is found. We use a convolutional neural network (CNN) to extract features from given images. Then GNN is used to find the similarity between each two feature vectors and complete the classification. Several subtasks consisting of randomly selected images are established to improve generalization of the model. The experiments are carried out on the dataset provided by Huashan Hospital. The dataset is labeled by postoperative pathological analysis and contains region of interest (ROI) information calibrated by experts. We set two tasks based on the dataset: benign or malignant diagnosis of PCNs and classification of specific types. Results Our model shows good performance on the two tasks with accuracies of 88.926% and 74.497%. The comparison of different methods' F1 scores in the benign or malignant diagnosis shows that the proposed GNN-based method effectively reduces the negative impact brought by imbalanced dataset, which is also verified by the macroaverage comparison in the four-class classification task. Conclusions Compared with existing models, the proposed GNN-based model shows better performance in terms of imbalanced dataset with small size while reducing labeling cost. The result provides a possibility for its application into the computer-aided diagnosis of PCNs.